Triple

T146313
Position Surface form Disambiguated ID Type / Status
Subject OpenAI E3337 entity
Predicate developed P73 FINISHED
Object GPT-3
GPT-3 is a large-scale autoregressive language model known for generating human-like text and performing a wide range of natural language tasks with minimal fine-tuning.
E18819 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: GPT-3 | Statement: [OpenAI, developed, GPT-3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: GPT-3
Context triple: [OpenAI, developed, GPT-3]
  • A. GPT-2
    GPT-2 is a large transformer-based language model known for generating coherent, human-like text and sparking widespread discussion about the implications of advanced AI text generation.
  • B. GPT-3.5
    GPT-3.5 is a large language model that generates human-like text and powers conversational AI applications such as advanced chatbots and coding assistants.
  • C. DALL·E
    DALL·E is an AI model developed by OpenAI that generates images from natural language descriptions, enabling text-to-image synthesis.
  • D. OpenAI
    OpenAI is an artificial intelligence research organization best known for developing advanced AI models such as ChatGPT and GPT series.
  • E. Claude
    Claude is a given name most famously associated with Claude Shannon, the American mathematician and electrical engineer known as the father of information theory.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: GPT-3
Triple: [OpenAI, developed, GPT-3]
Generated description
GPT-3 is a large-scale autoregressive language model known for generating human-like text and performing a wide range of natural language tasks with minimal fine-tuning.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: GPT-3
Target entity description: GPT-3 is a large-scale autoregressive language model known for generating human-like text and performing a wide range of natural language tasks with minimal fine-tuning.
  • A. GPT-2
    GPT-2 is a large transformer-based language model known for generating coherent, human-like text and sparking widespread discussion about the implications of advanced AI text generation.
  • B. GPT-3.5
    GPT-3.5 is a large language model that generates human-like text and powers conversational AI applications such as advanced chatbots and coding assistants.
  • C. DALL·E
    DALL·E is an AI model developed by OpenAI that generates images from natural language descriptions, enabling text-to-image synthesis.
  • D. OpenAI
    OpenAI is an artificial intelligence research organization best known for developing advanced AI models such as ChatGPT and GPT series.
  • E. Claude
    Claude is a given name most famously associated with Claude Shannon, the American mathematician and electrical engineer known as the father of information theory.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69a252868de4819080e21c9938bfe8b6 completed Feb. 28, 2026, 2:27 a.m.
NER Named-entity recognition batch_69a257ea7eac8190884a53453a9e0dd6 completed Feb. 28, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69a2ce36ad848190baf0359475fc0c3e completed Feb. 28, 2026, 11:15 a.m.
NEDg Description generation batch_69a2ceb2bd48819084fa2f198af74712 completed Feb. 28, 2026, 11:17 a.m.
NED2 Entity disambiguation (via description) batch_69a2cf98fc4881909e3e7cf0b90ae5ce completed Feb. 28, 2026, 11:20 a.m.
Created at: Feb. 28, 2026, 2:31 a.m.